The Data set consists of video game sales from 1980 to 2016 in different countries(North America, Europe, Japan and others) and regions. Overall, the data set consists of 16719 rows and 16 columns. It emphasizes on various features like publisher, developer, platform, critic score, user score, rating, genre of the games. Initially, during 1985 and 1992 the sales were very low. Gradually, the huge demand for video game sales started in the mid 90’s. Each video game consists of different kinds of ratings based on the genre like E= Everyone, AO= Adults only, E10+ = Everyone above 10+ age, EC = Early Childhood, M = Mature, T= Teen, RP= Rating Pending.

The below are the list of columns used in data set.

Name - Name of the game.
Platform - Game console.
Year_of_Release - Year of the Game's release date.
Genre - Game type (action, sports, etc.)
Publisher - Game studio.
NA_Sales - Sales in North America.
EU_Sales - Sales in Europe.
JP_Sales - Sales in japan.
Other_Sales - Sales in other regions.
Global_Sales - Sales around the globe.
Critic_score - Aggregate score compiled by Meta critic staff.
Critic_Count - The number of critics used in coming up with the Critic score.
User_Score - Score by Meta critic's subscribers.
User_Count - Number of users who gave the user score.
Developer - Party responsible for creating the game.
Rating - The ESRB ratings.

The above interactive line chart illustrates the number of video games released every year during 1980 to 2016 at 10-year interval. X-axis represents the year of release and Y-axis represents the count of video games. Initially, between 1980 to 1992 there were very a smaller count of games were released. Between 2002 to 2013 huge number of video games are released. In the year 2002 the video games released are more than 500, Unfortunately the count is dropped little bit in the years 2003 & 2004. Overall, we can observe that, between 2007 to 2011 the video game release count had drastically increased to 1400 approx. Year 2008 and 2009 records the highest number of games count.

The above interactive line graph represents the comparison of Global video game sale with North America, Europe, japan and other region sales. X-axis is represented as years and y-axis is represented as value. During 1980 and 1983 North America sales and Global sales are almost equal. Overall, irrespective of Global sales North America tops in video game sales as compared to Europe, japan and other regions. Europe had the moderate video game sales. As there is no data between 2017 to 2020, we can ignore.

The above interactive bar graph represents the number of games released in each Genre. From the above we can clearly say that Highest number of games are released in Action genre with count 3370 follower by sports genre. On the other side the least number of games released on Puzzle genre.

The correlation plot describes the correlation among the numeric variables in the given dataset. It is observed that there is high correlation among the sales. The correlation co-efficent between global sales and north america sales, europe sales is 0.96 and 0.94 respectively. The europe and north american sales are also highly correlated with the co-efficent of 0.84. The critic and user scores and counts are not significantly correlated.

The above scatter plot describes about the rating based of different games based Critic score and user score. We had choose only few ratings as other ratings have very data.The cricti score and user scores are almost same for few of the M(Mature) rating games.The least scores are for Entertaiment(E). Average score was given for E10+ and teen rating games. Score are given high for M rating games.

The above scatter plots demonstrates the user count and critic count based on genre. It is observed that for Role-Playing genre the user count is high but the critic count is low. on the hand for Action genre the user count is low but the crictc count is high. On an average the user count and critic count for all genrers are almost simlar.

The above plot illustrates the video game sales globally based on different genres. Sports genre has the highest number of sales compared with others and Adventure genre games shows very low sales. It is observed that Platform games stands in second in global sales followed by racing genre. other genres have average sales globally.

The above interactive barplot describes the top ten develops globally Is is observed that highest sales is for Nintendo developer and the tenth position is for Travellers tales. EA Sports grabs the second place in global sales. other developer sales are almost smilar.

CONCLUSION

After doing the EDA we conclude that Some games are available on various platforms, resulting in higher sales than games that are available on less platforms. The highest number of sales were reported for games published between 2006 and 2011, while sales were very low from the beginning of the 1980s to the mid-1990s. North America is the market with the highest revenue after global sales. Japan had the largest number of sales in 1995 as compared to other countries, but sales dropped dramatically after that.